Stock Price Prediction Research Articles

A Comparison of Statistical and Machine Learning Models for Stock Price Prediction

A Comparison of Statistical and Machine Learning Models for Stock Price Prediction

Enhancing Stock Price Prediction Using Mutual Information, PCA, and LSTM: A Deep Learning Approach

Enhancing Stock Price Prediction Using Mutual Information, PCA, and LSTM: A Deep Learning Approach

Forecasting Stock Prices with Artificial Intelligence

The purpose of this study is to investigate the closing prices of stocks in Artificial intelligence. The objective is to enhance the accuracy of future stock price Prediction to support investment or trading decisions. The models used in this paper include Simple Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), LSTM with peephole connectivity, and Gated Recurrent Unit (GRU). To conduct the study, Wal-Mart stock data is utilized to accurately predict future stock prices. The results show that the MSE for the SimpleRNN test is higher, indicating weaker generalization. The MSE of the basic LSTM test is lower than that of the RNN, indicating stronger generalization. The validated and tested MSEs of LSTM with peephole connectivity are higher than the basic LSTM and GRU. GRU performs as well as the basic LSTM but has the lowest LSTM training MSE. This stock prediction task requires the GRU model, which is the most suitable choice based on the training time.

Can technical Analysis Indicators Predict Future Stock Prices? Evidence from Elliot Wave and Fibonacci Retracement

Investors often find it challenging to track stock price fluctuations, especially when making decisions about buying and selling stocks. This study confirms and validates the Elliott wave scenario in analyzing the patterns of future stock price movements for PT Bank Central Asia Tbk and PT Bank Rakyat Indonesia Tbk. The primary focus is on the effectiveness of technical analysis in measuring medium-term price changes from 2020 to 2025, utilizing the Elliott wave oscillator and Fibonacci retracement tools. The findings indicate that BBCA's stock price in 2025 is likely to undergo a correction pattern, with a potential support area at the 50.00% retracement level of IDR 7,600. Meanwhile, BBRI's stock price movement in 2025 is expected to exhibit a bearish trend, with a support area at the 61.80% retracement level of IDR 3,770. Looking ahead, further research into stock price forecasting techniques would significantly contribute to the existing literature and provide valuable insights for investors and traders in predicting stock price movements.

금리 변동을 반영한 LSTM 기반 주가 예측 모델 연구

Due to the recent impact of inflation, central banks have maintained a policy of raising interest rates, highlighting the growing importance of financial market forecasting that reflects these economic conditions. However, there has been a lack of recent studies in Korea that consider interest rate in stock price prediction. In this study, we aimed to improve prediction accuracy by incorporating interest rates as a variable into stock price prediction models. For this purpose, we utilized the LSTM algorithm and trained the model on historical data from periods of high stock market volatility to predict the KOSPI index. Additionally, we conducted a multi-faceted analysis of the impact of interest rates through market conditions and sector-specific analyses. By employing various evaluation metrics, we performed both stock price prediction and directional movement prediction simultaneously. As a result, the model that incorporated interest rates demonstrated a 48.31% reduction in RMSE, compared to the baseline model, with the performance difference being statistically significant. This study confirms that interest rates are a critical variable in stock price prediction and that models reflecting interest rate fluctuations can enhance predictive performance.

Advancing Financial Forecasts: Stock Price Prediction Based on Time Series and Machine Learning Techniques

ABSTRACT Since the beginning of stock trading, investors and researchers have tried to find effective ways to predict the direction of stock prices on the next day. However, predicting stock prices is a hard task because there exist many factors that may affect the next day’s stock prices. Recently, investors and researchers have adopted machine learning techniques with technical indicator analysis to make prediction. But the prediction accuracy is unsatisfactory. Thus, this study aims to examine the problem of stock price prediction with time series and proposes an effective way to filter out the datasets, which consists of three key steps: First, a time series model with long-short-term memory (LSTM) was used to identify the possible problems and solve them in the process of stock price prediction. Second, the results of LSTM were adopted to influence the stock trend prediction by a variety of machine learning techniques, including random forest, support vector machine, light gradient boosting machine (LightGBM). Third, a novel method was proposed to select suitable datasets through buying or selling. Hereby, FTSE TWSE Taiwan 50 Index stocks were used as training and testing datasets, respectively. Some important days were selected for prediction and decision making. The experimental results show that the highest prediction accuracy of 86% and the average prediction accuracy of 82% have been obtained. Consequently, when comparing to other existing methods, the accuracy of predicting stock price trend with our proposed approach has been significantly improved. Reference No.: 2024-UAAI-0010R1/243667820 Subject Area: Intelligent Investment System

Predicting Stock Price Movements Using Deep Learning: An Analysis of Machine Learning Models for Portfolio Optimization

Capital markets play a strategic role in the global economy; however, high volatility often poses challenges for investors in making optimal investment decisions. Stock price prediction has become one of the key elements in effective portfolio management, but the complexity of market data demands more advanced analytical approaches. This study aims to explore the potential of Long Short-Term Memory (LSTM) models in predicting stock price movements and integrating these predictions into portfolio optimization strategies based on modern portfolio theory. The research methodology utilizes historical stock data from the S&P 500 and IDX Composite indices with daily frequency. The LSTM model is compared with Recurrent Neural Networks (RNN), Support Vector Machines (SVM), and Artificial Neural Networks (ANN) using metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and accuracy. The LSTM model demonstrated superior performance with an MSE of 0.0018, RMSE of 0.042, and prediction accuracy of 91.5%, significantly outperforming RNN (87.3%), SVM (80.2%), and ANN (82.7%). The prediction results were then integrated into portfolio optimization using the Mean-Variance Optimization approach, resulting in an increase in expected returns from 8.5% to 12.3%, a reduction in risk from 6.2% to 5.8%, and an improvement in the Sharpe ratio from 1.37 to 2.12. This study demonstrates that the LSTM model not only excels in stock price prediction accuracy but also contributes significantly to enhancing portfolio management efficiency. This Deep Learning-based approach offers a more adaptive, data-driven investment strategy, supporting more informed decision-making in the dynamic capital market

Monte Carlo Simulation Forecasting the Prices of Selected Stocks in the Automotive Sector

Investors are exposed to risk and uncertainty because of changes in financial markets’ prices. Investors perceive the risks associated with changes in the market prices as higher due to inaccuracy in predicting future returns because of fluctuations in prices. For this reason, they adopt different risk management methods that reduce or eliminate these risks. This research relies on Monte Carlo Simulation technique in predicting forthcoming yield rates from three companies operating under Turkish automotive segment namely, Dogus Automotive (DOAS), Tofas (TOASO) and Ford Otosan (FROTO). The simulation, which runs from January 1, 2023, to December 31, 2023, gives investors research-based insights that help them make strategic investment choices in times of high volatility in the market. According to the results, by modeling prospective future scenarios, MCS can be employed as a viable means of predicting stock prices in financial markets which subsequently helps people make rational investments thereby securing profitable ventures. Furthermore, this study offers practical suggestions in the form of MCS-generated volatility ranges. Investors can determine when it is advisable to buy or sell stocks in order to reduce potential losses and increase profits by setting realistic price objectives and allocating the portfolio differently in accordance with these calls.

Deep Learning and Variational Modal Decomposition in Stock Price Prediction

This study explores stock price forecasting, a critical topic for economic stability and investor decision-making. Traditional models like ARIMA struggle with stock market complexity due to their linear assumptions. To address this, the study examines advanced methods, focusing on deep learning techniques such as CNNs and LSTMs for their predictive strengths. It proposes a hybrid model combining Variational Mode Decomposition (VMD) and Bi-directional Long Short-Term Memory Networks (BiLSTM). VMD reduces time series non-stationarity, while BiLSTM captures sequence features via bi-directional processing. Empirical results show the VMD-BiLSTM model outperforms others in RMSE, MAE, and R² metrics, achieving higher forecasting accuracy. Although performance decreases during extreme price fluctuations, it effectively captures main trends. This research highlights the practical value of deep learning in handling complex financial time series and provides innovative methods for stock price prediction.

SP500 Forecast Based on ARIMA and ETS Models

Prediction of stock price, as a core issue in the financial sector, is deeply affected by the Federal Reserve's interest rate decision. As an important engine of the world economy, the United States' economic policies and decisions undoubtedly play a pivotal role on the global economic stage. The Fed's rate cut had a profound impact on global capital markets. Under the current macro background of the US interest rate cut, it is particularly critical to study and build an effective stock price forecasting model. In this paper, ARIMA and ETS models are used to predict SP500, and the results show that the RMSE value of ETS model fitting is lower than that of ARIMA model fitting. The ETS model can provide better prediction results in predicting SP500. This paper combines ARIMA and ETS models to provide a new perspective for stock price forecasting and a new idea for stock price forecasting under the background of US interest rate reduction.

Stock Price Prediction in the Financial Market Using Machine Learning Models

This paper presents an analysis of stock price forecasting in the financial market, with an emphasis on approaches based on time series models and deep learning techniques. Fundamental concepts of technical analysis are explored, such as exponential and simple averages, and various global indices are analyzed to be used as inputs for machine learning models, including Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Convolutional Neural Network (CNN), and XGBoost. The results show that while each model possesses distinct characteristics, selecting the most efficient approach heavily depends on the specific data and forecasting objectives. The complexity of advanced models such as XGBoost and GRU is reflected in their overall performance, suggesting that they can be particularly effective at capturing patterns and making accurate predictions in more complex time series, such as stock prices.

IMPLEMENTASI DATA MINING DALAM PREDIKSI HARGA SAHAM BBNI DENGAN PEMODELAN MATEMATIKA MENGGUNAKAN METODE LSTM DENGAN OPTIMASI ADAM

Stock price prediction plays a crucial role in investment decision-making, allowing investors to maximize profits and minimize risks. This study implements the Long Short-Term Memory (LSTM) method with Adam optimization to predict the stock price of Bank Negara Indonesia (BBNI) based on historical stock price data from the Indonesia Stock Exchange (2001-2023). LSTM is chosen for its ability to handle sequential data and identify long-term patterns in time series. Meanwhile, the Adam optimization algorithm is used to accelerate model convergence and improve prediction accuracy. The data used includes daily stock prices (closing prices), and the research process involves data collection, preprocessing, LSTM model creation, Adam optimization, training, evaluation, and prediction. The experimental results show that the model with a batch size of 64 and 100 epochs yields an R² of 0.9928 and a MAPE of 1.53%, indicating a very high prediction accuracy. With an accuracy of 98.46%, the LSTM model with Adam optimization proves to be effective in predicting stock prices, providing excellent results for applications in investment strategies. This study demonstrates the great potential of applying data mining and machine learning techniques in more informed and data-driven stock market analysis.

Comparative Analysis of Machine Learning Algorithms in Stock Price Prediction

Stock is part of a company's principal. A person who buys stock of a company shares the profit or loss of this company. Large volume transactions are made on stock exchanges where stocks are traded. Stock prices are difficult to predict because they are affected by many variables, but when they can be predicted, great benefits are provided. Prediction of stock prices is possible with today's computers using machine learning algorithms. Machine learning provides more successful results than fundamental and technical analysis in stock price prediction. In our study, daily closing price predictions were made by collecting approximately 5-years data of the top 5 stocks with the highest market value traded in BIST 100 between 2016 and 2020. Multiple linear regression, Bayesian regression, random forest, decision trees, support vector machines, artificial neural networks algorithms were applied to include maximum 22 features and the results were compared. The most successful result was obtained in the artificial neural networks algorithm. To achieve the highest success, data pre-processing, normalization, cross-validation, parameter optimization and feature selection were applied. It has been observed that using these methods together increases the success.

ANALISIS PREDIKSI HARGA SAHAM PT GUDANG GARAM TBK INDONESIA

This research aims to predict PT Gudang Garam Tbk's stock prices using the ARIMA method. Historical daily stock price data were analyzed to detect trends and seasonality. The ARIMA model was developed and tested, demonstrating significant predictive accuracy. Evaluation metrics such as Mean Absolute Error and Root Mean Squared Error were employed for performance assessment. The research contributes to stock price prediction methodologies, offering practical implications for investors and financial analysts. In conclusion, the study establishes a robust foundation for utilizing the ARIMA method in forecasting PT Gudang Garam Tbk's future stock prices.

Retraction Note: An optimal deep learning-based LSTM for stock price prediction using twitter sentiment analysis

Retraction Note: An optimal deep learning-based LSTM for stock price prediction using twitter sentiment analysis

STOCK PRICE PREDICTION FOR BANK SYARIAH INDONESIA USING BIDIRECTIONAL LONG SHORT-TERM MEMORY (BI-LSTM)

The evolution of global financial markets has heightened the demand for accurate stock price prediction methods, particularly in the Islamic banking sector, which operates under unique principles of Sharia compliance. This study aims to predict the stock prices of Bank Syariah Indonesia (BSI) using a Bidirectional Long Short-Term Memory (Bi-LSTM) model. The dataset comprises daily closing prices from January 2022 to June 2024. The model is optimized through systematic hyperparameter tuning, including configurations for the number of layers, neurons, batch size, learning rate, and optimizers. Evaluation using Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) identifies the Adam optimizer with a learning rate of 0.001 and batch size of 16 as the optimal configuration. The results highlight that while increasing the number of neurons or layers reduces minimum error, it increases model instability. This research provides novel insights into the application of Bi-LSTM for predicting Islamic banking stock prices, supporting data-driven decision-making in the Islamic financial sector.

Comparative Analysis of LSTM Variants for Stock Price Forecasting on NSE India: GRU's Dominance and Enhancements

The intricate realm of time series prediction using stock market datasets from the NSE India is delved into by this research. The supremacy of LSTM architecture for forecasting in time series is initially affirmed, only for a paradigm shift to be encountered when exploring various LSTM variants across distinct sectors on the NSE (National Stock Exchange) of India. Prices of various stocks in five different sectors have been predicted using multiple LSTM model variants. Contrary to the assumption that a specific variant would excel in a particular sector, the Gated Recurrent Unit (GRU) emerged as the top performer, prompting a closer examination of its limitations and subsequent enhancement using technical indicators. The ultimate objective is to unveil the most effective model for predicting stock prices in the dynamic landscape of NSE India.

Stock Price Prediction System LSTM Based on Deep Learning

Stock price prediction is a highly complex task due to the inherent volatility and non-linear patterns of financial markets. Recent advancements in deep learning, particularly Long Short-Term Memory (LSTM) networks, have yielded promising results in time series forecasting. This paper provides an in-depth analysis of LSTM models applied to the stock price prediction of major technology companies, including Apple (AAPL), Tesla (TSLA), Microsoft (MSFT), and Nvidia (NVDA). The study utilizes historical stock data to train and evaluate LSTM models, comparing their performance against various other regression models such as Linear Regression, Support Vector Regression (SVR), Decision Tree Regression, and Gradient Boosting Decision Trees (GBDT).The results demonstrate that the LSTM model outperforms traditional models, particularly in its ability to capture long-term dependencies and manage complex, volatile stock data. Among the companies analyzed, the LSTM model achieved the most accurate predictions for Apple, as indicated by the lowest Mean Squared Error (MSE). Tesla's predictions, while less accurate due to high volatility, still showed improvement compared to other models. In conclusion, the LSTM network proved to be the most effective method for stock price prediction in this study, particularly excelling in forecasting long-term trends and reducing prediction errors for volatile stocks.

Hybrid Preprocessing for Neural Network-Based Stock Price Prediction

In the domain of stock price prediction, the intricate interdependencies within multivariate time series data present significant challenges for accurate forecasting. This paper introduces a groundbreaking hybrid preprocessing technique to tackle this issue. By leveraging the Empirical Wavelet Transform (EWT), we adeptly extract both low-frequency and high-frequency components from the time series. We then apply Dynamic Time Warping (DTW) and Differential Dynamic Time Warping (DDTW) to measure component similarities, identifying correlated patterns within the stock price series. High-frequency components are managed using sliding windows and Principal Component Analysis (PCA), while PCA is directly applied to low-frequency components. Integrating these techniques into neural network models, our approach yields a substantial 30% improvement in prediction accuracy compared to traditional methods. This significant advancement underscores the potential of our hybrid preprocessing method in enhancing stock price prediction accuracy, offering valuable insights for financial market analysis.

Stock price prediction using the Sand Cat Swarm Optimization and an improved deep Long Short Term Memory network

Stock price prediction using the Sand Cat Swarm Optimization and an improved deep Long Short Term Memory network